{"ID":2840984,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.12578","arxiv_id":"2511.12578","title":"TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Prediction","abstract":"We present TempoMaster, a novel framework that formulates long video generation as next-frame-rate prediction. Specifically, we first generate a low-frame-rate clip that serves as a coarse blueprint of the entire video sequence, and then progressively increase the frame rate to refine visual details and motion continuity. During generation, TempoMaster employs bidirectional attention within each frame-rate level while performing autoregression across frame rates, thus achieving long-range temporal coherence while enabling efficient and parallel synthesis. Extensive experiments demonstrate that TempoMaster establishes a new state-of-the-art in long video generation, excelling in both visual and temporal quality.","short_abstract":"We present TempoMaster, a novel framework that formulates long video generation as next-frame-rate prediction. Specifically, we first generate a low-frame-rate clip that serves as a coarse blueprint of the entire video sequence, and then progressively increase the frame rate to refine visual details and motion continui...","url_abs":"https://arxiv.org/abs/2511.12578","url_pdf":"https://arxiv.org/pdf/2511.12578v3","authors":"[\"Yukuo Ma\",\"Cong Liu\",\"Junke Wang\",\"Junqi Liu\",\"Haibin Huang\",\"Zuxuan Wu\",\"Chi Zhang\",\"Xuelong Li\"]","published":"2025-11-16T12:41:07Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}